Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ptr
    -0.07
    fact
    -0.06
     Organization
    -0.06
     Hornets
    -0.06
    )!=
    -0.06
    .date
    -0.06
     for
    -0.06
    éf
    -0.06
    [
    -0.06
     typu
    -0.06
    POSITIVE LOGITS
    _sessions
    0.07
    …the
    0.07
     письмен
    0.06
    cales
    0.06
    нут
    0.06
    /The
    0.06
    ников
    0.06
     inject
    0.06
    .Version
    0.06
    .parsers
    0.06
    Act Density 0.029%

    No Known Activations